期刊
JOURNAL OF COMPUTATIONAL BIOLOGY
卷 29, 期 8, 页码 892-907出版社
MARY ANN LIEBERT, INC
DOI: 10.1089/cmb.2021.0598
关键词
Alzheimer's disease; canonical correlation analysis; deep neural networks; multi-omics; supervised learning
类别
资金
- Bio and Medical Technology Development Program of NRF - Korean government (MSIT) [NRF-2018M3C7A1054935]
- Institute of Information and Communications Technology Planning and Evaluation (IITP) - Korean government (MSIT) [2019-0-01842]
Integration of multi-omics data using the proposed supervised deep generalized canonical correlation analysis (SDGCCA) method improves phenotypic classification and biomarker identification. By considering complex/nonlinear cross-data correlations between multiple modalities, SDGCCA outperforms other methods in predicting Alzheimer's disease (AD) and discriminating early- and late-stage cancers. Additionally, SDGCCA enables feature selection and identifies important multi-omics biomarkers associated with AD.
Integration of multi-omics data provides opportunities for revealing biological mechanisms related to certain phenotypes. We propose a novel method of multi-omics integration called supervised deep generalized canonical correlation analysis (SDGCCA) for modeling correlation structures between nonlinear multi-omics manifolds that aims at improving the classification of phenotypes and revealing the biomarkers related to phenotypes. SDGCCA addresses the limitations of other canonical correlation analysis (CCA)-based models (such as deep CCA, deep generalized CCA) by considering complex/nonlinear cross-data correlations between multiple (>= 2) modalities. Although there are a few methods to learn nonlinear CCA projections for classifying phenotypes, they only consider two views. Methods extended to multiple views either do not perform classification or do not provide feature ranking. In contrast, SDGCCA is a nonlinear multi-view CCA projection method that performs classification and ranks features. When we applied SDGCCA in predicting patients with Alzheimer's disease (AD) and discrimination of early- and late-stage cancers, it outperformed other CCA-based and other supervised methods. In addition, we demonstrate that SDGCCA can be applied for feature selection to identify important multi-omics biomarkers. On applying AD data, SDGCCA identified clusters of genes in multi-omics data, well known to be associated with AD.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据